Cover Image

Optimal robust estimation for discrete time stochastic processes

In this paper a general method of constructing robust quasi-likelihood estimating functions for discrete time stochastic processes is given. Examples of a regression model with autoregressive errors and a general contamination model are presented to illustrate the methodology. The loss of efficiency involved in robustification is also discussed.
Year of publication:
1987
Authors: Kulkarni, P.M. ; Heyde, C.C.
Published in:
Stochastic Processes and their Applications. - Elsevier, ISSN 0304-4149. - Vol. 26.1987, p. 267-276
Publisher: Elsevier
Keywords: estimating function optimality score function generalized M-estimation contamination autoregressive processes robust quasi-likelihood
Type of publication: Article
Source:
Persistent link: https://www.econbiz.de/10008875465
Similar items by person